Back to Registry
rubric.code.logic_correct
SOFT
LLM-judge rubric verifier scoring code logic correctness on 4 criteria: algorithm, edge cases, logic errors, requirements.
Scorecard
| Determinism | stochastic-judge |
| Evidence Quality | judge-opinion |
| Intended Use | eval-and-train |
| Gating Required | Yes |
| Recommended Gates | |
| Permissions | None |
Test Fixtures
9 total
| Type | Count |
|---|---|
| Positive | 3 |
| Negative | 3 |
| Adversarial | 3 |
Metadata
| Version | 0.1.0 |
| Domain | rubric |
| Task Type | code_logic_review |
| Contributor | vr.dev |
| Source | tobysimonds.com/research/2025/09/29/Proofs.html |
Use in SDK
# CLI
vr verify --verifier rubric.code.logic_correct --ground-truth '{"order_id": "ORD-42"}'
# Python
from vrdev import verify
result = verify("rubric.code.logic_correct", ground_truth={"order_id": "ORD-42"})
# API
curl -X POST https://api.vr.dev/v1/verify \
-H "X-API-Key: vr_live_..." \
-d '{"verifier": "rubric.code.logic_correct", "ground_truth": {"order_id": "ORD-42"}}'